{"id":"https://openalex.org/W7127312443","doi":"https://doi.org/10.48550/arxiv.2602.01186","title":"The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics","display_name":"The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127312443","doi":"https://doi.org/10.48550/arxiv.2602.01186"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.01186","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124879109","display_name":"Fabio Turazza","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Turazza, Fabio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124964706","display_name":"Marco Picone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Picone, Marco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124945722","display_name":"Marco Mamei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mamei, Marco","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124879109"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9258000254631042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9258000254631042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.7832000255584717},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6040999889373779},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.5685999989509583},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4754999876022339},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.44029998779296875},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.3995000123977661},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.3919000029563904},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964000105857849},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7832000255584717},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6040999889373779},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C178518018","wikidata":"https://www.wikidata.org/wiki/Q1024555","display_name":"CUSUM","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.01186","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.01186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.01186","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Classical":[0],"Federated":[1],"Learning":[2],"relies":[3],"on":[4,67,148,172],"a":[5,42,71,97,141,160],"multi-round":[6],"iterative":[7],"process":[8],"of":[9,70,99,107],"model":[10,27,84],"exchange":[11],"and":[12,16,22,48,117,120,157,184],"aggregation":[13],"between":[14],"server":[15,122],"clients,":[17],"with":[18,144],"high":[19],"communication":[20,40],"costs":[21],"privacy":[23],"risks":[24],"from":[25,135],"repeated":[26],"transmissions.":[28],"In":[29,176],"contrast,":[30],"one-shot":[31,55,100],"federated":[32,101],"learning":[33],"(OFL)":[34],"alleviates":[35],"these":[36,88],"limitations":[37],"by":[38],"reducing":[39],"to":[41],"single":[43],"round,":[44],"thereby":[45],"lowering":[46],"overhead":[47],"enhancing":[49],"practical":[50],"deployability.":[51],"Nevertheless,":[52],"most":[53],"existing":[54],"approaches":[56],"remain":[57],"either":[58],"impractical":[59],"or":[60,78,83],"constrained,":[61],"for":[62],"example,":[63],"they":[64],"often":[65],"depend":[66],"the":[68,92,121,136],"availability":[69],"public":[72],"dataset,":[73],"assume":[74,104],"homogeneous":[75],"client":[76],"models,":[77],"require":[79],"uploading":[80],"additional":[81],"data":[82],"information.":[85],"To":[86],"overcome":[87],"issues,":[89],"we":[90],"introduce":[91],"Gaussian-Head":[93],"OFL":[94],"(GH-OFL)":[95],"family,":[96],"suite":[98],"methods":[102,180],"that":[103,165],"class-conditional":[105],"Gaussianity":[106],"pretrained":[108],"embeddings.":[109],"Clients":[110],"transmit":[111],"only":[112],"sufficient":[113],"statistics":[114],"(per-class":[115],"counts":[116],"first/second-order":[118],"moments)":[119],"builds":[123],"heads":[124,131],"via":[125,169],"three":[126],"components:":[127],"(i)":[128],"Closed-form":[129],"Gaussian":[130,167],"(NB/LDA/QDA)":[132],"computed":[133],"directly":[134],"received":[137],"statistics;":[138],"(ii)":[139],"FisherMix,":[140],"linear":[142],"head":[143,164],"cosine":[145],"margin":[146],"trained":[147],"synthetic":[149,174],"samples":[150],"drawn":[151],"in":[152],"an":[153],"estimated":[154],"Fisher":[155],"subspace;":[156],"(iii)":[158],"Proto-Hyper,":[159],"lightweight":[161],"low-rank":[162],"residual":[163],"refines":[166],"logits":[168],"knowledge":[170],"distillation":[171],"those":[173],"samples.":[175],"our":[177],"experiments,":[178],"GH-OFL":[179],"deliver":[181],"state-of-the-art":[182],"robustness":[183],"accuracy":[185],"under":[186],"strong":[187],"non-IID":[188],"skew":[189],"while":[190],"remaining":[191],"strictly":[192],"data-free.":[193]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-04T00:00:00"}